econ401 final project R Notebook

Libraries:

library(tidyverse)

Registered S3 method overwritten by 'dplyr':
  method           from
  print.rowwise_df     
-- Attaching packages --------------------------------------- tidyverse 1.2.1 --
v ggplot2 3.2.1     v purrr   0.3.3
v tibble  2.1.3     v dplyr   0.8.3
v tidyr   1.0.0     v stringr 1.4.0
v readr   1.3.1     v forcats 0.4.0
-- Conflicts ------------------------------------------ tidyverse_conflicts() --
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

library(readr)
library(rvest)

Loading required package: xml2

Attaching package: 㤼㸱rvest㤼㸲

The following object is masked from 㤼㸱package:purrr㤼㸲:

    pluck

The following object is masked from 㤼㸱package:readr㤼㸲:

    guess_encoding

library(stats)
library(readxl)
library(dplyr)
library(stringr)
library(ggplot2)
library(ggthemes)

package 㤼㸱ggthemes㤼㸲 was built under R version 3.6.2

library(stringr)
library(data.table)

Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
data.table 1.12.6 using 4 threads (see ?getDTthreads).  Latest news: r-datatable.com

Attaching package: 㤼㸱data.table㤼㸲

The following objects are masked from 㤼㸱package:dplyr㤼㸲:

    between, first, last

The following object is masked from 㤼㸱package:purrr㤼㸲:

    transpose

library(geojsonio)

Attaching package: 㤼㸱geojsonio㤼㸲

The following object is masked from 㤼㸱package:base㤼㸲:

    pretty

library(leaflet)

Registered S3 methods overwritten by 'htmltools':
  method               from         
  print.html           tools:rstudio
  print.shiny.tag      tools:rstudio
  print.shiny.tag.list tools:rstudio
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

library(rgdal)

Loading required package: sp
rgdal: version: 1.4-7, (SVN revision 845)
 Geospatial Data Abstraction Library extensions to R successfully loaded
 Loaded GDAL runtime: GDAL 2.2.3, released 2017/11/20
 Path to GDAL shared files: C:/Users/neris/OneDrive/Documents/R/win-library/3.6/rgdal/gdal
 GDAL binary built with GEOS: TRUE 
 Loaded PROJ.4 runtime: Rel. 4.9.3, 15 August 2016, [PJ_VERSION: 493]
 Path to PROJ.4 shared files: C:/Users/neris/OneDrive/Documents/R/win-library/3.6/rgdal/proj
 Linking to sp version: 1.3-1 

library(haven)
library(stargazer)

Please cite as: 

 Hlavac, Marek (2018). stargazer: Well-Formatted Regression and Summary Statistics Tables.
 R package version 5.2.2. https://CRAN.R-project.org/package=stargazer 

Data:

Model 3:

First making a graph of annual GDP highs and lows – maybe a temporary proxy for recessions?

Annual enrollment graph:

Join enrollment data and gdp data to create linear model test:

Graph it?

College Proximity Question 5/3: (Reading in Ivy’s data)

cz <- read_dta('cz.dta')

Error in read_dta("cz.dta") : could not find function "read_dta"

Read in/create mobility data: (Trends in Mobility: Commuting Zone Intergenerational Mobility Estimates by Birth Cohort) https://opportunityinsights.org/data/?geographic_level=101&topic=0&paper_id=0#resource-listing

Read in geojson file:

Commuting zones on the map (cz.geojson@data) are in 1990s format. They need to be converted so our post-2000 data can be connected to the shapefiles: (https://www.ers.usda.gov/data-products/commuting-zones-and-labor-market-areas/)

Making the map actually display data:

cz.geo %>%
  leaflet() %>%
  addTiles() %>%
  addPolygons(fillColor = ~colors1(cz.geo@data$ncollege),
              weight = 1,
              color = "white",
              opacity = 0.5,
              fillOpacity = .7) %>%
  setView(-96, 37.8, 3) %>%
  addLegend(pal = colors1,
            values = cz.geo@data$ncollege,
            title = "Number of Colleges in Commuting Zone")

Some values were outside the color scale and will be treated as NA

Try to run some lms:

Ivy’s STATA code:

foreach x of varlist ncollege nfouryr nfouryrpriv npub nelite hascollege{
    
foreach y of varlist kfr_pooled_pooled_p1 kfr_pooled_pooled_p25 kfr_pooled_pooled_p50 kfr_pooled_pooled_p75 kfr_pooled_pooled_p100 {
    reg `y' `x' popdensity2010 med_hhinc2016, r 
    outreg2 using `x'_kfr, excel append ctitle(`y')
}

Variables of interest:

as.formula(paste0(yvar1, " ~ ", paste0(xvars1, collapse =  " + ")))

kfr_pooled_pooled_p1 ~ ncollege + nfouryr + nfouryrpriv + npub + 
    nelite + hascollege + popdensity2010 + med_hhinc2016

testing?

stargazer(lm.kfr_p1,
          type = "text",
          dep.var.labels = c("kfr_pooled_pooled_p1"))

length of NULL cannot be changedlength of NULL cannot be changedlength of NULL cannot be changedlength of NULL cannot be changedlength of NULL cannot be changed

===============================================
                        Dependent variable:    
                    ---------------------------
                                kfr            
-----------------------------------------------
ncollege                       0.003           
                              (0.004)          
                                               
nfouryr                       0.007*           
                              (0.004)          
                                               
nfouryrpriv                  -0.012***         
                              (0.004)          
                                               
npub                         -0.011***         
                              (0.004)          
                                               
nelite                         0.006           
                              (0.005)          
                                               
hascollege                   -0.049***         
                              (0.006)          
                                               
popdensity2010              -0.0001***         
                             (0.00001)         
                                               
med_hhinc2016               0.00000***         
                             (0.00000)         
                                               
Constant                     0.251***          
                              (0.012)          
                                               
-----------------------------------------------
Observations                    741            
R2                             0.281           
Adjusted R2                    0.273           
Residual Std. Error      0.062 (df = 732)      
F Statistic           35.756*** (df = 8; 732)  
===============================================
Note:               *p<0.1; **p<0.05; ***p<0.01

nelite on kfr at different levels

htmtable.nelite <- stargazer(nelite.p1, nelite.p25, nelite.p50, nelite.p75, nelite.p100,
          type = "html",
          dep.var.labels = c("Bottom 1%", "25%", "50%", "75%", "Top 1%"),
          out = "nelitetable.html")

length of NULL cannot be changedlength of NULL cannot be changedlength of NULL cannot be changedlength of NULL cannot be changedlength of NULL cannot be changed

<table style="text-align:center"><tr><td colspan="6" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left"></td><td colspan="5"><em>Dependent variable:</em></td></tr>
<tr><td></td><td colspan="5" style="border-bottom: 1px solid black"></td></tr>
<tr><td style="text-align:left"></td><td>Bottom 1%</td><td>25%</td><td>50%</td><td>75%</td><td>Top 1%</td></tr>
<tr><td style="text-align:left"></td><td>(1)</td><td>(2)</td><td>(3)</td><td>(4)</td><td>(5)</td></tr>
<tr><td colspan="6" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left">nelite</td><td>-0.004</td><td>-0.002</td><td>-0.001</td><td>0.001</td><td>0.004</td></tr>
<tr><td style="text-align:left"></td><td>(0.003)</td><td>(0.003)</td><td>(0.002)</td><td>(0.002)</td><td>(0.003)</td></tr>
<tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td><td></td></tr>
<tr><td style="text-align:left">popdensity2010</td><td>-0.0001<sup>***</sup></td><td>-0.0001<sup>***</sup></td><td>-0.00004<sup>***</sup></td><td>-0.00002<sup>***</sup></td><td>-0.00000</td></tr>
<tr><td style="text-align:left"></td><td>(0.00001)</td><td>(0.00001)</td><td>(0.00001)</td><td>(0.00001)</td><td>(0.00001)</td></tr>
<tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td><td></td></tr>
<tr><td style="text-align:left">med_hhinc2016</td><td>0.00000<sup>***</sup></td><td>0.00000<sup>***</sup></td><td>0.00000<sup>***</sup></td><td>0.00000</td><td>-0.00000<sup>***</sup></td></tr>
<tr><td style="text-align:left"></td><td>(0.00000)</td><td>(0.00000)</td><td>(0.00000)</td><td>(0.00000)</td><td>(0.00000)</td></tr>
<tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td><td></td></tr>
<tr><td style="text-align:left">Constant</td><td>0.221<sup>***</sup></td><td>0.350<sup>***</sup></td><td>0.471<sup>***</sup></td><td>0.585<sup>***</sup></td><td>0.770<sup>***</sup></td></tr>
<tr><td style="text-align:left"></td><td>(0.012)</td><td>(0.010)</td><td>(0.009)</td><td>(0.009)</td><td>(0.009)</td></tr>
<tr><td style="text-align:left"></td><td></td><td></td><td></td><td></td><td></td></tr>
<tr><td colspan="6" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left">Observations</td><td>741</td><td>741</td><td>741</td><td>741</td><td>741</td></tr>
<tr><td style="text-align:left">R<sup>2</sup></td><td>0.141</td><td>0.104</td><td>0.055</td><td>0.016</td><td>0.030</td></tr>
<tr><td style="text-align:left">Adjusted R<sup>2</sup></td><td>0.137</td><td>0.100</td><td>0.051</td><td>0.012</td><td>0.026</td></tr>
<tr><td style="text-align:left">Residual Std. Error (df = 737)</td><td>0.068</td><td>0.057</td><td>0.050</td><td>0.047</td><td>0.053</td></tr>
<tr><td style="text-align:left">F Statistic (df = 3; 737)</td><td>40.261<sup>***</sup></td><td>28.387<sup>***</sup></td><td>14.380<sup>***</sup></td><td>4.096<sup>***</sup></td><td>7.651<sup>***</sup></td></tr>
<tr><td colspan="6" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left"><em>Note:</em></td><td colspan="5" style="text-align:right"><sup>*</sup>p<0.1; <sup>**</sup>p<0.05; <sup>***</sup>p<0.01</td></tr>
</table>

image print cheeeeck:

tables %>%
  ggplot() +
  geom_bar(stat = "identity") +
  geom_image(aes(image = picture),
             size = .2)

Error: geom_bar requires the following missing aesthetics: x, y

Plotting the lms:

Wait lemme try the long format thing:

write_csv(data_long1a, "long_kfr.csv")

Error in is.data.frame(x) : object 'data_long1a' not found

Output table:

stargazer(long.lm1,
          type = "text")

length of NULL cannot be changedlength of NULL cannot be changedlength of NULL cannot be changedlength of NULL cannot be changedlength of NULL cannot be changed

===============================================
                        Dependent variable:    
                    ---------------------------
                                kfr            
-----------------------------------------------
ncollege                     -0.001***         
                             (0.0003)          
                                               
black                        -0.099***         
                              (0.004)          
                                               
white                        0.023***          
                              (0.003)          
                                               
popdensity2010              -0.00001**         
                             (0.00001)         
                                               
med_hhinc2016               0.00000***         
                             (0.00000)         
                                               
Constant                     0.478***          
                              (0.007)          
                                               
-----------------------------------------------
Observations                  10,250           
R2                             0.119           
Adjusted R2                    0.119           
Residual Std. Error     0.142 (df = 10244)     
F Statistic         276.960*** (df = 5; 10244) 
===============================================
Note:               *p<0.1; **p<0.05; ***p<0.01

Try with interaction & w/o hhinc:

summary(long.lm1a)

Call:
lm(formula = kfr ~ ncollege + black + white + black * ncollege + 
    white * ncollege + popdensity2010 + med_hhinc2016, data = long.data1a)

Residuals:
     Min       1Q   Median       3Q      Max 
-0.39850 -0.10502 -0.01114  0.09142  0.85434 

Coefficients:
                     Estimate Std. Error t value Pr(>|t|)    
(Intercept)         4.787e-01  7.168e-03  66.775  < 2e-16 ***
ncollege           -1.284e-03  4.290e-04  -2.993  0.00277 ** 
blackTRUE          -1.006e-01  3.960e-03 -25.394  < 2e-16 ***
whiteTRUE           2.189e-02  3.629e-03   6.031 1.69e-09 ***
popdensity2010     -1.494e-05  7.062e-06  -2.116  0.03440 *  
med_hhinc2016       9.841e-07  1.429e-07   6.888 5.99e-12 ***
ncollege:blackTRUE  4.269e-04  5.166e-04   0.826  0.40862    
ncollege:whiteTRUE  4.141e-04  5.091e-04   0.814  0.41594    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.142 on 10242 degrees of freedom
  (865 observations deleted due to missingness)
Multiple R-squared:  0.1192,    Adjusted R-squared:  0.1186 
F-statistic: 197.9 on 7 and 10242 DF,  p-value: < 2.2e-16

No significant difference. Will stick to original model.

Visualize it maybe?:

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.